Abstract
In this paper we present an application of machine learning to generating natural language route directions. We use the TAG formalism to represent the structure of the generated texts and split the generation process into a number of individual tasks which can be modeled as classification problems. To solve each of these tasks we apply corpus-trained classifiers relying on semantic and contextual features, determined for each task in a feature selection procedure.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baker, C.F., Fillmore, C.J., Lowe, J.B.: The Berkeley FrameNet project. In: Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics, Montréal, Québec, Canada, August 10-14, pp. 86–90 (1998)
Moens, M., Steedman, M.: Temporal ontology and temporal reference. Computational Linguistics 14, 15–28 (1988)
Vendler, Z.: Verbs and times. In: Linguistics in Philosophy, pp. 97–121. Cornell University Press, Ithaca (1967)
Joshi, A.K., Schabes, Y.: Tree-adjoining grammars and lexicalized grammars. In: Nivat, M., Podelski, A. (eds.) Definability and Recognizability of Sets of Trees, Elsevier, Amsterdam (1991)
Stone, M., Doran, C.: Sentence planning as description using tree adjoining grammar. In: Proceedings of the Thirty-Fifth Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics, Madrid, Spain, July 7-12, pp. 198–205 (1997)
Bleam, T., Palmer, M., Shanker, V.: Motion verbs and semantic features in TAG. In: Proceedings of the 4th International Workshop on Tree-adjoining Grammars and Related Frameworks (TAG+), Philadelphia, PA, August 1-3 (1998)
Webber, B.L., Joshi, A.: Anchoring a lexicalized tree-adjoining grammar for discourse. In: Proceedings of the COLING/ACL 1998 Workshop on Discourse Relations and Discourse Markers, Montréal, Québec, Canada, August 15, pp. 86–92 (1998)
Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artificial Intelligence Journal 97, 273–324 (1997)
Cleary, J.G., Trigg, L.E.: K*: An instance-based learner using an entropic distance measure. In: Proceedings of the 12th International Conference on Machine Learning, Tahoe City, Ca, July 9-12, pp. 108–114 (1995)
Witten, I.H., Frank, E.: Data Mining - Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco (2000)
Cohen, W.W.: Fast effective rule induction. In: Proceedings of the 12th International Conference on Machine Learning, Tahoe City, Ca, July 9-12, pp. 115–123 (1995)
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)
Langkilde, I., Knight, K.: Generation that exploits corpus-based statistical knowledge. In: Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics, Montréal, Québec, Canada, August 10-14, pp. 704–710 (1998)
Bangalore, S., Rambow, O.: Exploiting a probabilistic hierarchical model for generation. In: Proceedings of the 18th International Conference on Computational Linguistics, Saarbrücken, Germany, July 31– 4 August, pp. 42–48 (2000)
Varges, S., Mellish, C.: Instance-based natural language generation. In: Proceedings of the 2nd Meeting of the North American Chapter of the Association for Computational Linguistics, Pittsburgh, PA, June 2-7, pp. 1–8 (2001)
Duboue, P.K., McKeown, K.R.: Empirically estimating order constraints for content planning in generation. In: Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics, Toulouse, France, July 9-11, pp. 172–179 (2001)
Dimitromanolaki, A., Androutsopoulos, I.: Learning to order facts for discourse planning in natural language generation. In: Proceedings of the 9th European Workshop on Natural Language Generation, Budapest, Hungary, April 13 -14, pp. 23–30 (2003)
Chen, J., Bangalore, S., Rambow, O., Walker, M.: Towards automatic generation of natural language generation systems. In: Proceedings of the 19th International Conference on Computational Linguistics, Taipei, Taiwan, August 24 -1 September (2002)
Daelemans, W., van den Bosch, A.: Rapid development of NLP modules with memory based learning. In: Proceedings of ELSNET in Wonderland, pp. 105–113. ELSNET, Utrecht (1998)
Hardt, D., Rambow, O.: Generation of VP ellipsis: A corpus-based approach. In: Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics, Toulouse, France, July 9-11, pp. 282–289 (2001)
Bangalore, S., Rambow, O., Whittaker, S.: Evaluation metrics for generation. In: Proceedings of the 1st International Natural Language Generation Conference, Mitzpe Ramon, Israel, June 12 -16, pp. 1–8 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Marciniak, T., Strube, M. (2004). Classification-Based Generation Using TAG. In: Belz, A., Evans, R., Piwek, P. (eds) Natural Language Generation. INLG 2004. Lecture Notes in Computer Science(), vol 3123. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27823-8_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-27823-8_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22340-5
Online ISBN: 978-3-540-27823-8
eBook Packages: Springer Book Archive